Model: TwIL 8B balanced

WebAI released TwIL 8B balanced, an 8.8B-parameter reasoning model post-trained from IBM Granite 4.2 8B for maths, code and instruction following, under a webAI licence limited to non-commercial research and education. The checkpoint ships as a single GGUF Q4_K_M file of 5.35 GB (5,347,917,568 bytes) with a 131K maximum context, and at 4K context it needs about 6.3 GB of VRAM — 5.1 GB of weights, 0.63 GB of KV cache and a 0.6 GB activation buffer — because all 40 layers keep a growing KV cache. webAI has not published quantization quality loss for the model, and the verbose checkpoint is a separate set of weights not mixed into these levels.

TwIL 8B balanced 8.8B webAI TwIL A reasoning model for maths, code and instruction following, post-trained from IBM Granite 4.2 8B. This entry is the balanced checkpoint only; verbose is a distinct set of weights and its files are not mixed into these levels. All 40 layers keep a growing KV cache. The webAI licence permits non-commercial research and education only. Quantization quality loss has not been published. 131K Max Context 1 Quant Variants GGUF Q4 K M Best Quality — Perplexity rise best build Quantization Variants Per-quant VRAM, quality loss, and inference speed on RTX 4090 Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports Which file each size is for A file size is not a memory figure: the VRAM column is the calculator's total at 4K context — weights plus KV cache plus a 10% activation buffer. Units differ on purpose: file sizes are decimal GB, as Hugging Face lists them; the VRAM column is GiB 1024³ bytes with 2% added to the weights, so 7.12 GB of file counts as about 6.8 GiB there. A vision projector mmproj , where the repo ships one, is a separate download and is in neither number. - GGUF Q4 K M webAI-Official/TwIL-8B https://huggingface.co/webAI-Official/TwIL-8B · TwIL-8B-Q4 K M-balanced.gguf · 5.35 GB 5,347,917,568 bytes · listing read 2026-11-15 Related community runs These runs describe their own settings. Their speeds do not replace this estimate or prove your configuration fits. Our reviewed link index has no run for this model yet. You can browse community reports or share your own test below. Browse more runs on llamaPerf ↗ https://llamaperf.com/ Similar models Compare with Qwen3.5 9B https://quantized.uk/tools/compare/?a=twil-8b-balanced&b=qwen3-5-9b 9BConsumer GPUMac / Apple SiliconQ4 K M6.6 GB—perplexity rise https://quantized.uk/quant-hub/qwen3-5-9b/ Qwen3.5 9B Alibaba Qwen3.5 The newest small Qwen and a common pick for 8 to 16 GB cards. Only 8 of its 32 layers keep a growing KV cache, so it can use a long context on modest hardware. At Q4 K M it needs about 6.6 GB at 4K and 7.0 GB at 16K, comfortable on an 8 GB card; at 32K 7.5 GB it is tight there and comfortable from 10 GB up. Its full 256K window needs about 15.2 GB. Q8 0 needs about 10.4 GB, comfortable from 12 GB up. Reasoning is off by default on the small Qwen3.5 sizes, and it reads images through a separate vision encoder. Sizes come from the published GGUF file sizes, and no per-level quality loss has been published. 8BConsumer GPUMac / Apple SiliconQ4 K M6.5 GB—perplexity rise https://quantized.uk/quant-hub/granite-4.2-8b/ Granite 4.2 8B IBM Granite IBM's dense 8B reasoning model from the Granite 4.2 family 3B, 8B, 30B , released in August under Apache 2.0. Thinking is on by default; a non-thinking and a low-effort mode are chosen through the chat template. Unlike Granite 4.0's hybrid models it is a plain transformer, so llama.cpp runs it as granite and every one of its 40 layers keeps a full cache: about 6.5 GB at Q4 K M with a 4K context, 11.3 GB at 32K and 27.8 GB across the whole 128K window. That makes it an 8 GB card model at short contexts and a 16 GB one for long documents. Sizes come from bartowski's GGUF files; IBM publishes no perplexity by quantization level, so no quality-loss figure is shown. 14BConsumer GPUMac / Apple SiliconQ4 K M10.1 GB+2.9%perplexity rise https://quantized.uk/quant-hub/qwen2.5-14b/ Qwen2.5 14B Instruct Alibaba Qwen2.5 The sweet spot between performance and resource usage. 16GB VRAM with Q4. 14BConsumer GPUMac / Apple SiliconQ4 K M9.7 GB+3.0%perplexity rise https://quantized.uk/quant-hub/phi-3-medium-14b/ Phi-3 Medium 14B Instruct Microsoft Phi Microsoft's mid-size Phi-3. Excellent quality-per-GB on 16GB cards. Running TwIL 8B balanced locally At Q4 K M and 4K of context, TwIL 8B balanced needs about 6.3 GB — 5.1 GB of weights, 0.63 GB of KV cache and a 0.6 GB activation buffer. The smallest cards in this index that clear that comfortably are 8 GB ones — 9 of them, from the RTX 4060 up — and 76 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs. What longer context costs Going from 4K to 32K adds about 4.37 GB, taking the total to 11.1 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4 K M would need about 28 GB. Which build to download This index only tracks TwIL 8B balanced in GGUF, across 1 level Q4 K M . No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving. Common questions - How much VRAM does TwIL 8B balanced need? - About 6.3 GB at Q4 K M with 4K of context and batch 1, rising to roughly 11.1 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card. - Will TwIL 8B balanced run on a 8GB GPU? - Yes — at Q4 K M and 4K context it needs about 6.3 GB, which leaves 1.7 GB spare on a RTX 4060, or on any of the other 8 GB cards here 9 in all . That is the smallest size in this index that clears it comfortably; 76 of 78 do. - Which quantization of TwIL 8B balanced should I use? - Q4 K M is the only level in the index for this model, so there is nothing to choose between here. Where this model fits Sized at Q4 K M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory. - Runs comfortably on - RTX 40608GB · +1.7 https://quantized.uk/gpu/rtx-4060/ RTX 4060 Ti 8G8GB · +1.7 https://quantized.uk/gpu/rtx-4060-ti-8g/ Radeon RX 9060 XT 8G8GB · +1.7 https://quantized.uk/gpu/radeon-rx-9060-xt-8g/ RTX 5060 Ti 8G8GB · +1.7 https://quantized.uk/gpu/rtx-5060-ti-8g/ RTX 50608GB · +1.7 https://quantized.uk/gpu/rtx-5060/ - Tight but possible - Mac M1 8G8GB https://quantized.uk/gpu/mac-m1-8g/ Mac M3 8G8GB https://quantized.uk/gpu/mac-m3-8g/ - Ships in - GGUF https://quantized.uk/formats/gguf/ - Try it yourself - Size it in the calculator https://quantized.uk/tools/vram-calc/?model=twil-8b-balanced&quant=Q4 K M Generate the run command https://quantized.uk/tools/cli-gen/?model=twil-8b-balanced&quant=Q4 K M How to actually run this Deployment guides for this model and this class of hardware. This page's figures change when the model or the runtime does.Last updated 2026-11-15 RSS → /feed.xml https://quantized.uk/feed.xml